{"id":"W2031600655","doi":"10.1109/3pgcic.2012.38","title":"Large-Scale Mining of Co-occurrences: Challenges and Solutions","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Set (abstract data type); Pruning; Field (mathematics); Hash function; Scale (ratio); Database transaction; Data mining; Principal (computer security); Word (group theory); Information retrieval; Association rule learning; Core (optical fiber); Data science; Theoretical computer science; Database; Computer security; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002627469,0.00004708108,0.0000710231,0.00003335371,0.00008578377,0.0000184038,0.0002335155,0.00002083168,0.00001192349],"category_scores_gemma":[0.000009470663,0.00003990111,0.00001339573,0.00007784409,0.00003761421,0.0003908152,0.0001501896,0.00002904994,0.00001217351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000282705,"about_ca_system_score_gemma":0.00001170002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000499168,"about_ca_topic_score_gemma":0.000008051272,"domain_scores_codex":[0.9994888,0.00001198806,0.00009732572,0.0001260879,0.00007994636,0.0001958532],"domain_scores_gemma":[0.9995602,0.00006009558,0.00003654216,0.0002491123,0.00002080295,0.00007321782],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[2.751655e-7,0.0002145914,0.001145401,0.00001633901,0.00001035675,1.052199e-7,0.01320251,6.559753e-7,0.0001291522,0.602863,0.003270122,0.3791475],"study_design_scores_gemma":[0.001212558,0.0002830469,0.1702974,0.0001567919,0.0000494423,0.00007719824,0.02693622,0.3015462,0.004008458,0.00578592,0.4885174,0.001129346],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02150732,0.00715826,0.9388771,0.001673879,0.0001776755,0.0001041886,0.00006335961,0.0001439785,0.03029422],"genre_scores_gemma":[0.6845773,0.0005712791,0.3145723,0.0000542267,0.00005798694,0.00001873616,0.0000070272,0.000002947992,0.0001381588],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.66307,"threshold_uncertainty_score":0.162712,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07059073906538048,"score_gpt":0.2994183145528519,"score_spread":0.2288275754874714,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}